Environmental_case_study

Libraries

library(tidyverse)

## ── Attaching packages ───────────────────────────────────────── tidyverse 1.2.1 ──

## ✓ ggplot2 3.3.0     ✓ purrr   0.3.3
## ✓ tibble  2.1.3     ✓ dplyr   0.8.3
## ✓ tidyr   1.0.0     ✓ stringr 1.4.0
## ✓ readr   1.3.1     ✓ forcats 0.4.0

## ── Conflicts ──────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library(readxl)
library(plotly)

## 
## Attaching package: 'plotly'

## The following object is masked from 'package:ggplot2':
## 
##     last_plot

## The following object is masked from 'package:stats':
## 
##     filter

## The following object is masked from 'package:graphics':
## 
##     layout

library(gganimate)
library(RColorBrewer)

Wrangling the data

Global Data

Yearly CO₂ Emissions, 1000 Metric Tonnes

Source

Click here to be redirected to the source from which we obtained this dataset

Click here to be redirected to the direct source for this dataset

Code

library(here)

## here() starts at /Users/carriewright/Documents/GitHub/ocs-CO2/ocs-bloomberg-emissions-case-study

CO2_emissions <- read_excel(here("docs/yearly_co2_emissions_1000_tonnes.xlsx"))

head(CO2_emissions)

## # A tibble: 6 x 265
##   country `1751` `1752` `1753` `1754` `1755` `1756` `1757` `1758` `1759`
##   <chr>    <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>
## 1 Afghan…     NA     NA     NA     NA     NA     NA     NA     NA     NA
## 2 Albania     NA     NA     NA     NA     NA     NA     NA     NA     NA
## 3 Algeria     NA     NA     NA     NA     NA     NA     NA     NA     NA
## 4 Andorra     NA     NA     NA     NA     NA     NA     NA     NA     NA
## 5 Angola      NA     NA     NA     NA     NA     NA     NA     NA     NA
## 6 Antigu…     NA     NA     NA     NA     NA     NA     NA     NA     NA
## # … with 255 more variables: `1760` <dbl>, `1761` <dbl>, `1762` <dbl>,
## #   `1763` <dbl>, `1764` <dbl>, `1765` <dbl>, `1766` <dbl>, `1767` <dbl>,
## #   `1768` <dbl>, `1769` <dbl>, `1770` <dbl>, `1771` <dbl>, `1772` <dbl>,
## #   `1773` <dbl>, `1774` <dbl>, `1775` <dbl>, `1776` <dbl>, `1777` <dbl>,
## #   `1778` <dbl>, `1779` <dbl>, `1780` <dbl>, `1781` <dbl>, `1782` <dbl>,
## #   `1783` <dbl>, `1784` <dbl>, `1785` <dbl>, `1786` <dbl>, `1787` <dbl>,
## #   `1788` <dbl>, `1789` <dbl>, `1790` <dbl>, `1791` <dbl>, `1792` <dbl>,
## #   `1793` <dbl>, `1794` <dbl>, `1795` <dbl>, `1796` <dbl>, `1797` <dbl>,
## #   `1798` <dbl>, `1799` <dbl>, `1800` <dbl>, `1801` <dbl>, `1802` <dbl>,
## #   `1803` <dbl>, `1804` <dbl>, `1805` <dbl>, `1806` <dbl>, `1807` <dbl>,
## #   `1808` <dbl>, `1809` <dbl>, `1810` <dbl>, `1811` <dbl>, `1812` <dbl>,
## #   `1813` <dbl>, `1814` <dbl>, `1815` <dbl>, `1816` <dbl>, `1817` <dbl>,
## #   `1818` <dbl>, `1819` <dbl>, `1820` <dbl>, `1821` <dbl>, `1822` <dbl>,
## #   `1823` <dbl>, `1824` <dbl>, `1825` <dbl>, `1826` <dbl>, `1827` <dbl>,
## #   `1828` <dbl>, `1829` <dbl>, `1830` <dbl>, `1831` <dbl>, `1832` <dbl>,
## #   `1833` <dbl>, `1834` <dbl>, `1835` <dbl>, `1836` <dbl>, `1837` <dbl>,
## #   `1838` <dbl>, `1839` <dbl>, `1840` <dbl>, `1841` <dbl>, `1842` <dbl>,
## #   `1843` <dbl>, `1844` <dbl>, `1845` <dbl>, `1846` <dbl>, `1847` <dbl>,
## #   `1848` <dbl>, `1849` <dbl>, `1850` <dbl>, `1851` <dbl>, `1852` <dbl>,
## #   `1853` <dbl>, `1854` <dbl>, `1855` <dbl>, `1856` <dbl>, `1857` <dbl>,
## #   `1858` <dbl>, `1859` <dbl>, …

CO2_emissions <- CO2_emissions %>%
  gather(key = Year, value = Emissions, -country) %>%
  rename(Country=country) %>%
  mutate(Emissions = Emissions/1000) %>%
  rename(`CO2 Emissions (Mg)`=Emissions)

sapply(CO2_emissions, class)

##            Country               Year CO2 Emissions (Mg) 
##        "character"        "character"          "numeric"

CO2_emissions$Year <- as.numeric(CO2_emissions$Year)

summary(CO2_emissions$Year)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    1751    1817    1882    1882    1948    2014

ggplot(CO2_emissions, aes(x=Year, y=`CO2 Emissions (Mg)`, group=Country)) +
  geom_line(alpha=0.2) + 
  labs(title = expression("Country CO"[2]*" Emissions per Year , 1751-2014"),
       caption = expression("Limited to reporting countries")) + 
  ylab("Emissions (1M Metric Tonnes)")

## Warning: Removed 33099 row(s) containing missing values (geom_path).

CO2_emissions %>%
  group_by(Year) %>%
  summarise(`CO2 Emissions (Mg)` = sum(`CO2 Emissions (Mg)`, na.rm = TRUE)) %>%
  ggplot(aes(x=Year, y=`CO2 Emissions (Mg)`)) +
  geom_line() + 
  labs(title = expression("World CO"[2]*" Emissions per Year , 1751-2014"),
       caption = expression("Limited to reporting countries")) + 
  ylab("Emissions (1M Metric Metric Tonnes)")

Yearly Growth in GDP per Capita

Source

Click here to be redirected to the source from which we obtained this dataset

Click here to be redirected to the direct source for this dataset

Code

Michael Need to determine units for this

gdp_growth <- read_xlsx(here("docs/gdp_per_capita_yearly_growth.xlsx"))

head(gdp_growth)

## # A tibble: 6 x 220
##   country   `1801`   `1802`   `1803`   `1804`   `1805`   `1806`   `1807`
##   <chr>      <dbl>    <dbl>    <dbl>    <dbl>    <dbl>    <dbl>    <dbl>
## 1 Afghan… NA       NA       NA       NA       NA       NA       NA      
## 2 Albania  0.104    0.104    0.104    0.104    0.104    0.104    0.104  
## 3 Algeria -0.00247 -0.00247 -0.00247 -0.00247 -0.00247 -0.00247 -0.00247
## 4 Andorra  0.166    0.166    0.166    0.166    0.166    0.166    0.166  
## 5 Angola   0.425    0.425    0.425    0.425    0.425    0.425    0.425  
## 6 Antigu… NA       NA       NA       NA       NA       NA       NA      
## # … with 212 more variables: `1808` <dbl>, `1809` <dbl>, `1810` <dbl>,
## #   `1811` <dbl>, `1812` <dbl>, `1813` <dbl>, `1814` <dbl>, `1815` <dbl>,
## #   `1816` <dbl>, `1817` <dbl>, `1818` <dbl>, `1819` <dbl>, `1820` <dbl>,
## #   `1821` <dbl>, `1822` <dbl>, `1823` <dbl>, `1824` <dbl>, `1825` <dbl>,
## #   `1826` <dbl>, `1827` <dbl>, `1828` <dbl>, `1829` <dbl>, `1830` <dbl>,
## #   `1831` <dbl>, `1832` <dbl>, `1833` <dbl>, `1834` <dbl>, `1835` <dbl>,
## #   `1836` <dbl>, `1837` <dbl>, `1838` <dbl>, `1839` <dbl>, `1840` <dbl>,
## #   `1841` <dbl>, `1842` <dbl>, `1843` <dbl>, `1844` <dbl>, `1845` <dbl>,
## #   `1846` <dbl>, `1847` <dbl>, `1848` <dbl>, `1849` <dbl>, `1850` <dbl>,
## #   `1851` <dbl>, `1852` <dbl>, `1853` <dbl>, `1854` <dbl>, `1855` <dbl>,
## #   `1856` <dbl>, `1857` <dbl>, `1858` <dbl>, `1859` <dbl>, `1860` <dbl>,
## #   `1861` <dbl>, `1862` <dbl>, `1863` <dbl>, `1864` <dbl>, `1865` <dbl>,
## #   `1866` <dbl>, `1867` <dbl>, `1868` <dbl>, `1869` <dbl>, `1870` <dbl>,
## #   `1871` <dbl>, `1872` <dbl>, `1873` <dbl>, `1874` <dbl>, `1875` <dbl>,
## #   `1876` <dbl>, `1877` <dbl>, `1878` <dbl>, `1879` <dbl>, `1880` <dbl>,
## #   `1881` <dbl>, `1882` <dbl>, `1883` <dbl>, `1884` <dbl>, `1885` <dbl>,
## #   `1886` <dbl>, `1887` <dbl>, `1888` <dbl>, `1889` <dbl>, `1890` <dbl>,
## #   `1891` <dbl>, `1892` <dbl>, `1893` <dbl>, `1894` <dbl>, `1895` <dbl>,
## #   `1896` <dbl>, `1897` <dbl>, `1898` <dbl>, `1899` <dbl>, `1900` <dbl>,
## #   `1901` <dbl>, `1902` <dbl>, `1903` <dbl>, `1904` <dbl>, `1905` <dbl>,
## #   `1906` <dbl>, `1907` <dbl>, …

gdp_growth <- gdp_growth %>%
  gather(key = Year, value = gdp_growth, -country) %>%
  rename(Country=country) %>%
  rename(`GDP Growth/Capita (%)` = gdp_growth) %>%
  filter(complete.cases(.))

sapply(gdp_growth, class)

##               Country                  Year GDP Growth/Capita (%) 
##           "character"           "character"             "numeric"

gdp_growth$Year <- as.numeric(gdp_growth$Year)

summary(gdp_growth$Year)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    1801    1863    1915    1915    1967    2019

ggplot(gdp_growth, aes(x=Year, y=`GDP Growth/Capita (%)`, group=Country)) +
  geom_line(alpha=0.2) + 
  labs(title = expression("Country GDP Growth per Capita per Year (Annual %), 1801-2019"),
       caption = expression("Limited to reporting countries")) + 
  ylab("GDP Growth per Capita (Annual %)")

gdp_growth %>%
  group_by(Year) %>%
  summarise(`GDP Growth/Capita (%)` = mean(`GDP Growth/Capita (%)`, na.rm = TRUE)) %>%
  ggplot(aes(x=Year, y=`GDP Growth/Capita (%)`)) +
  geom_line() + 
  labs(title = expression("Mean Country GDP Growth per Capita per Year (Annual %), 1801-2019"),
       caption = expression("Limited to reporting countries")) + 
  ylab("GDP Growth per Capita (Annual %)")

Energy Use per Person

Source

Click here to be redirected to the source from which we obtained this dataset

Click here to be redirected to the direct source for this dataset

Code

energy_use <- read_xlsx(here("docs/energy_use_per_person.xlsx"))

head(energy_use)

## # A tibble: 6 x 57
##   country `1960` `1961` `1962` `1963` `1964` `1965` `1966` `1967` `1968`
##   <chr>    <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>
## 1 Albania     NA     NA     NA     NA     NA     NA     NA     NA     NA
## 2 Algeria     NA     NA     NA     NA     NA     NA     NA     NA     NA
## 3 Angola      NA     NA     NA     NA     NA     NA     NA     NA     NA
## 4 Antigu…     NA     NA     NA     NA     NA     NA     NA     NA     NA
## 5 Argent…     NA     NA     NA     NA     NA     NA     NA     NA     NA
## 6 Armenia     NA     NA     NA     NA     NA     NA     NA     NA     NA
## # … with 47 more variables: `1969` <dbl>, `1970` <dbl>, `1971` <dbl>,
## #   `1972` <dbl>, `1973` <dbl>, `1974` <dbl>, `1975` <dbl>, `1976` <dbl>,
## #   `1977` <dbl>, `1978` <dbl>, `1979` <dbl>, `1980` <dbl>, `1981` <dbl>,
## #   `1982` <dbl>, `1983` <dbl>, `1984` <dbl>, `1985` <dbl>, `1986` <dbl>,
## #   `1987` <dbl>, `1988` <dbl>, `1989` <dbl>, `1990` <dbl>, `1991` <dbl>,
## #   `1992` <dbl>, `1993` <dbl>, `1994` <dbl>, `1995` <dbl>, `1996` <dbl>,
## #   `1997` <dbl>, `1998` <dbl>, `1999` <dbl>, `2000` <dbl>, `2001` <dbl>,
## #   `2002` <dbl>, `2003` <dbl>, `2004` <dbl>, `2005` <dbl>, `2006` <dbl>,
## #   `2007` <dbl>, `2008` <dbl>, `2009` <dbl>, `2010` <dbl>, `2011` <dbl>,
## #   `2012` <dbl>, `2013` <dbl>, `2014` <dbl>, `2015` <dbl>

energy_use <- energy_use %>%
  gather(key = Year, value = energy_use, -country) %>%
  rename(Country=country) %>%
  rename(`Energy Use (kg, oil-eq./capita)` = energy_use)

sapply(energy_use, class)

##                         Country                            Year 
##                     "character"                     "character" 
## Energy Use (kg, oil-eq./capita) 
##                       "numeric"

energy_use$Year <- as.numeric(energy_use$Year)

summary(energy_use$Year)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    1960    1974    1988    1988    2001    2015

ggplot(energy_use, aes(x=Year, y=`Energy Use (kg, oil-eq./capita)`, group=Country)) +
  geom_line(alpha=0.2) + 
  labs(title = expression("Country Energy Use (kg of Oil Equivalent per Capita), 1960-2015",),
       caption = expression("Limited to reporting countries")) + 
  ylab("Energy Use (kg of Oil Equivalent per Capita)")

## Warning: Removed 3203 row(s) containing missing values (geom_path).

energy_use %>%
  group_by(Year) %>%
  summarise(`Energy Use (kg, oil-eq./capita)` = sum(`Energy Use (kg, oil-eq./capita)`, na.rm = TRUE)) %>%
  ggplot(aes(x=Year, y=`Energy Use (kg, oil-eq./capita)`)) +
  geom_line() + 
  labs(title = expression("Worldwide Energy Use (kg of Oil Equivalent per Capita), 1960-2015"),
       caption = expression("Limited to reporting countries")) + 
  ylab("Energy Use (kg of Oil Equivalent per Capita)")

Crude Mortality Rate

Source

Click here to be redirected to the direct source for this dataset

Code

mortality <- read_xls(here("docs/API_SP.DYN.CDRT.IN_DS2_en_excel_v2_804384.xls"))

## New names:
## * `` -> ...3
## * `` -> ...4
## * `` -> ...5
## * `` -> ...6
## * `` -> ...7
## * … and 57 more problems

head(mortality)

## # A tibble: 6 x 64
##   `Data Source` `World Developm… ...3  ...4  ...5  ...6  ...7  ...8  ...9 
##   <chr>         <chr>            <chr> <chr> <chr> <chr> <chr> <chr> <chr>
## 1 Last Updated… 43819            <NA>  <NA>  <NA>  <NA>  <NA>  <NA>  <NA> 
## 2 <NA>          <NA>             <NA>  <NA>  <NA>  <NA>  <NA>  <NA>  <NA> 
## 3 Country Name  Country Code     Indi… Indi… 1960  1961  1962  1963  1964 
## 4 Aruba         ABW              Deat… SP.D… 6.38… 6.24… 6.11… 6.01… 5.91…
## 5 Afghanistan   AFG              Deat… SP.D… 32.2… 31.6… 31.0… 30.5… 30.0…
## 6 Angola        AGO              Deat… SP.D… 27.0… 26.8… 26.6… 26.4… 26.1…
## # … with 55 more variables: ...10 <chr>, ...11 <chr>, ...12 <chr>,
## #   ...13 <chr>, ...14 <chr>, ...15 <chr>, ...16 <chr>, ...17 <chr>,
## #   ...18 <chr>, ...19 <chr>, ...20 <chr>, ...21 <chr>, ...22 <chr>,
## #   ...23 <chr>, ...24 <chr>, ...25 <chr>, ...26 <chr>, ...27 <chr>,
## #   ...28 <chr>, ...29 <chr>, ...30 <chr>, ...31 <chr>, ...32 <chr>,
## #   ...33 <chr>, ...34 <chr>, ...35 <chr>, ...36 <chr>, ...37 <chr>,
## #   ...38 <chr>, ...39 <chr>, ...40 <chr>, ...41 <chr>, ...42 <chr>,
## #   ...43 <chr>, ...44 <chr>, ...45 <chr>, ...46 <chr>, ...47 <chr>,
## #   ...48 <chr>, ...49 <chr>, ...50 <chr>, ...51 <chr>, ...52 <chr>,
## #   ...53 <chr>, ...54 <chr>, ...55 <chr>, ...56 <chr>, ...57 <chr>,
## #   ...58 <chr>, ...59 <chr>, ...60 <chr>, ...61 <chr>, ...62 <chr>,
## #   ...63 <chr>, ...64 <chr>

colnames(mortality) <- mortality[3,]
mortality <- mortality[-c(1:3),]

mortality <- mortality %>%
  select(-`Country Code`,
         -`Indicator Name`,
         -`Indicator Code`) %>%
  rename(Country="Country Name") %>%
  gather(key = Year, value = `Deaths/1000 People`, -Country)

sapply(mortality, class)

##            Country               Year Deaths/1000 People 
##        "character"        "character"        "character"

mortality$Year <- as.numeric(mortality$Year)
mortality$`Deaths/1000 People` <- as.numeric(mortality$`Deaths/1000 People`)

summary(mortality$Year)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    1960    1975    1990    1990    2004    2019

ggplot(mortality, aes(x=Year, y=`Deaths/1000 People`, group=Country)) +
  geom_line(alpha=0.2) + 
  labs(title = expression("Country Crude Mortality Rate (per 1000 Persons), 1960-2019",),
       caption = expression("Limited to reporting countries")) + 
  ylab("Crude Mortality Rate (per 1000 Persons)")

## Warning: Removed 1477 row(s) containing missing values (geom_path).

mortality %>%
  group_by(Year) %>%
  summarise(`Deaths/1000 People` = mean(`Deaths/1000 People`, na.rm = TRUE)) %>%
  ggplot(aes(x=Year, y=`Deaths/1000 People`)) +
  geom_line() + 
  labs(title = expression("Mean Country Crude Mortality Rate (per 1000 Persons), 1960-2019",),
       caption = expression("Limited to reporting countries")) + 
  ylab("Crude Mortality Rate (per 1000 Persons)")

## Warning: Removed 2 row(s) containing missing values (geom_path).

US-specific Data

Disasters

Source

Click here to be redirected to the direct source for this dataset

Code

us_disaster <- read_csv(here("docs/time-series-US.csv"), skip = 2)

## Parsed with column specification:
## cols(
##   .default = col_double()
## )

## See spec(...) for full column specifications.

us_disaster <- us_disaster %>%
  dplyr::select(Year,
                `Drought Count`,
                `Flooding Count`,
                `Freeze Count`,
                `Severe Storm Count`,
                `Tropical Cyclone Count`,
                `Wildfire Count`,
                `Winter Storm Count`)

sapply(us_disaster, class)

##                   Year          Drought Count         Flooding Count 
##              "numeric"              "numeric"              "numeric" 
##           Freeze Count     Severe Storm Count Tropical Cyclone Count 
##              "numeric"              "numeric"              "numeric" 
##         Wildfire Count     Winter Storm Count 
##              "numeric"              "numeric"

us_disaster <- us_disaster %>%
  mutate(`Disasters` = rowSums(.[2:dim(.)[2]])) %>%
  dplyr::select(Year,
                `Disasters`) %>%
  mutate(Country="United States") %>%
  gather(key = Indicator, value = Value, -Country, -Year) %>%
  mutate(Region="United States",
         Type="US-specific")

Temperature

Source

Click here to be redirected to the direct source for this dataset

Code

us_temperature <- read_csv(here("docs/temperature.txt"),skip=4,na="-99")

## Parsed with column specification:
## cols(
##   Date = col_double(),
##   Value = col_double(),
##   Anomaly = col_double()
## )

sapply(us_temperature, class)

##      Date     Value   Anomaly 
## "numeric" "numeric" "numeric"

us_temperature <- us_temperature %>%
  dplyr::select(-Anomaly) %>%
  mutate(Date = substr(Date, start = 1, stop = 4)) %>%
  mutate(Country="United States",
         Year = Date,
         Indicator="Temperature (Fahrenheit)",
         Region="United States",
         Type="US-specific") %>%
  dplyr::select(-Date, )

Analysis dataframe

colnames(CO2_emissions)

## [1] "Country"            "Year"               "CO2 Emissions (Mg)"

colnames(gdp_growth)

## [1] "Country"               "Year"                  "GDP Growth/Capita (%)"

colnames(energy_use)

## [1] "Country"                         "Year"                           
## [3] "Energy Use (kg, oil-eq./capita)"

colnames(mortality)

## [1] "Country"            "Year"               "Deaths/1000 People"

df_wide <- CO2_emissions %>%
  full_join(gdp_growth, by=c("Country", "Year")) %>%
  full_join(energy_use, by=c("Country", "Year")) %>%
  full_join(mortality, by=c("Country", "Year"))

df_long <- df_wide %>%
  gather(key=Indicator,value=Value,-Country, -Year) %>%
  mutate(Region=case_when(Country=="United States" ~ "United States",
                          Country!="United States" ~ "Rest of the World"),
         Type="Global")

setequal(sapply(df_long, class),sapply(us_disaster, class))

## [1] TRUE

setequal(sapply(df_long, class),sapply(us_temperature, class))

## [1] TRUE

df_long <- df_long %>%
  rbind(us_disaster) %>%
  rbind(us_temperature)

sapply(df_long,class)

##     Country        Year   Indicator       Value      Region        Type 
## "character" "character" "character"   "numeric" "character" "character"

df_long$Country <- as.factor(df_long$Country)
df_long$Year <- as.numeric(df_long$Year)

sapply(df_long,class)

##     Country        Year   Indicator       Value      Region        Type 
##    "factor"   "numeric" "character"   "numeric" "character" "character"

df_long <- df_long %>%
  filter(complete.cases(.)) %>%
  arrange(Country)

ggplot(df_long, aes(x=Year, y=Value, group=Country)) +
  geom_line(alpha=0.2) + 
  facet_grid(Indicator~., scales = "free_y") +
  ylab("Indicator Value") + 
  labs(title="Distribution of Indicators by Year and Value")

Subsetting the data

df_long %>%
  filter(Type=="Global") %>%
  group_by(Year,Indicator) %>%
  tally() %>%
  ggplot(aes(x=Year, y=n, color=Indicator)) +
  geom_vline(xintercept = 1980, linetype=2, color="black") +
  geom_vline(xintercept = 2010, linetype=2, color="black") +
  geom_line() +
  labs(title = "Countries with Complete Data per Year",
       subtitle = "Global Data") + 
  ylab("Countries") + 
  scale_x_continuous(breaks = seq(1750,2020,by=10),
                     labels = seq(1750,2020,by=10)) +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 90),
        axis.title.x = element_blank(),
        legend.position = "bottom")

df_long %>%
  filter(Region=="United States") %>%
  group_by(Indicator) %>%
  summarise(Start=min(Year), End=max(Year)) %>%
  ggplot(aes(x=Indicator, y=End)) +
  geom_hline(yintercept = 1980, linetype=2, color="black") +
  geom_hline(yintercept = 2010, linetype=2, color="black") +
  geom_segment(aes(x=Indicator,
                   xend=Indicator,
                   yend=End,
                   y=Start)) +
  geom_point(aes(x=Indicator, y=Start), shape=16, color="black") +
  geom_point(aes(x=Indicator, y=End), shape=21, fill="white", color="black") + 
  coord_flip() +
  labs(title = "Complete Data per Year",
       subtitle = "US-specific Data") + 
  ylab("Countries") + 
  scale_y_continuous(breaks = seq(1750,2020,by=10),
                     labels = seq(1750,2020,by=10)) +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 90),
        axis.title = element_blank())

animation_1 <- df_long %>%
  filter(Type=="Global") %>%
  filter(Indicator=="Deaths/1000 People") %>%
  filter(Year>=1980) %>%
  filter(Year<=2010) %>%
  ggplot(aes(x=Year, y=Value, group=Country, color=Region, size=Region,alpha=Region)) +
  geom_point() +
  scale_color_manual(values = c("Red","Black")) +
  scale_alpha_manual(values = c(0.1, 1)) +
  scale_size_manual(values = c(0.25, 2)) +
  labs(title="Distribution of Indicators by Year and Value, 1980-2010") +
  theme(axis.text.x = element_text(angle = 90)) + 
  theme_classic() +
  ylab("Crude Mortality Rate") +
  transition_time(as.integer(Year)) +
  shadow_wake(wake_length = 1, alpha = FALSE)

animate(animation_1, fps = 10, duration = 5)

animation_2 <- df_long %>%
  filter(Type=="Global") %>%
  filter(Indicator=="Energy Use (kg, oil-eq./capita)") %>%
  filter(Year>=1980) %>%
  filter(Year<=2010) %>%
  ggplot(aes(x=Year, y=Value, group=Country, color=Region, size=Region, alpha=Region)) +
  geom_point() +
  scale_color_manual(values = c("Red","Black")) +
  scale_alpha_manual(values = c(0.1, 1)) +
  scale_size_manual(values = c(0.25, 2)) +
  labs(title="Distribution of Indicators by Year and Value, 1980-2010") +
  theme_classic() +
  theme(axis.text.x = element_text(angle = 90)) + 
  ylab("Energy Use per Capita") +
  transition_time(as.integer(Year)) +
  shadow_wake(wake_length = 1, alpha = FALSE)

animate(animation_2, fps = 10, duration = 5)

animation_3 <- df_long %>%
  filter(Type=="Global") %>%
  filter(Indicator=="GDP Growth/Capita (%)") %>%
  filter(Year>=1980) %>%
  filter(Year<=2010) %>%
  ggplot(aes(x=Year, y=Value, group=Country, color=Region, size=Region, alpha=Region)) +
  geom_point() +
  scale_color_manual(values = c("Red","Black")) +
  scale_alpha_manual(values = c(0.1, 1)) +
  scale_size_manual(values = c(0.25, 2)) +
  labs(title="Distribution of Indicators by Year and Value, 1980-2010") +
  theme_classic() +
  theme(axis.text.x = element_text(angle = 90)) +
  ylab("GDP Growth per Capita (%)") +
  transition_time(as.integer(Year)) +
  shadow_wake(wake_length = 1, alpha = FALSE)

animate(animation_3, fps = 10, duration = 5)

animation_4 <- df_long %>%
  filter(Type=="Global") %>%
  filter(Indicator=="CO2 Emissions (Mg)") %>%
  filter(Year>=1980) %>%
  filter(Year<=2010) %>%
  ggplot(aes(x=Year, y=Value, group=Country, color=Region, size=Region, alpha=Region)) +
  geom_point() +
  scale_color_manual(values = c("Red","Black")) +
  scale_alpha_manual(values = c(0.1, 1)) +
  scale_size_manual(values = c(0.25, 2)) +
  labs(title="Distribution of Indicators by Year and Value, 1980-2010") +
  theme_classic() +
  theme(axis.text.x = element_text(angle = 90)) +
  ylab("CO2 Emissions (Mg)") +
  transition_time(as.integer(Year)) +
  shadow_wake(wake_length = 1, alpha = FALSE)

animate(animation_4, fps = 10, duration = 5)

df_long %>%
  filter(Type=="Global") %>%
  filter(Indicator=="CO2 Emissions (Mg)") %>%
  filter(Year>=1900) %>%
  filter(Year<=2010) %>%
  group_by(Country) %>%
  mutate(max_val = max(Value)) %>%
  ungroup() %>%
  mutate(rank=dense_rank(-max_val)) %>%
  filter(rank<=10) %>%
  ggplot(aes(x=Year, y=fct_reorder(Country, Value, max))) +
  geom_tile(color="transparent", aes(fill=log(Value))) +
  scale_fill_gradientn(colors = c("yellow","red","black")) +
  scale_x_continuous(breaks = seq(1900,2010,by=5),
                     labels = seq(1900,2010,by=5)) + 
  theme_classic() + 
  theme(axis.text.x = element_text(angle = 90),
        axis.title = element_blank(),
        legend.position = "bottom") + 
  labs(title = "Top 10 Emissions-producing Countries in 2010 (1900-2010)",
       subtitle = "Ordered by Emissions Produced in 2010",
       fill = "Ln(CO2 Emissions (Mg))")

US-specific

df_long_us <- df_long %>%
  filter(Country=="United States")

# Approximated derivative function)
df_long_us <- df_long_us %>%
  filter(Year>=1900,
         Year<=2010) %>%
  group_by(Indicator) %>%
  mutate("Change (%)"=((Value/lag(Value))*100)-100,
         Mean=mean(Value),
         Anomaly=Value-Mean) %>%
  ungroup() %>%
  mutate(Anomaly_color=ifelse(Anomaly>0,"Positive",
                              ifelse(Anomaly<0,"Negative","Zero")),
         Anomaly_color=factor(Anomaly_color, levels = c("Positive",
                                                        "Negative",
                                                        "Zero"),
                              ordered = TRUE))

df_long_us %>%
  filter(Year>=1980) %>%
  filter(Year<=2010) %>%
  ggplot(aes(x=Year, y=Value)) + 
  geom_line() + 
  facet_wrap(Indicator~., ncol=2, nrow=3, scales = "free_y") + 
  scale_x_continuous(breaks = seq(1980,2010,by=5),
                     labels = seq(1980,2010,by=5)) +
  theme_classic() + 
  theme(axis.text.x = element_text(angle = 90),
        axis.title.y = element_blank()) + 
  labs(title = "US-specific Indicators (1980-2010)")

df_long_us %>%
  filter(Year>=1980) %>%
  filter(Year<=2010) %>%
  ggplot(aes(x=Year, y=`Change (%)`, color=Indicator, fill="transparent")) + 
  geom_hline(yintercept=0.8, linetype=2) +
  geom_hline(yintercept=1.2, linetype=2) +
  geom_hline(yintercept = 1, linetype=3) +
  geom_line(size=0.5) + 
  scale_x_continuous(breaks = seq(1980,2010,by=5),
                     labels = seq(1980,2010,by=5)) +
  scale_y_continuous(breaks = seq(-500,1250, by=250),
                     labels = seq(-500,1250, by=250)) +
  theme_classic() +
  theme(axis.text.x = element_text(angle = 90),
        axis.title.x  = element_blank(),
        legend.position = "bottom",
        legend.direction = "horizontal") + 
  labs(title = "US-specific Indicators (1980-2010)",
       subtitle = "Change (%) Lines")

## Warning: Removed 1 row(s) containing missing values (geom_path).

df_long_us %>%
  filter(Year>=1980) %>%
  filter(Year<=2010) %>%
  filter(Indicator=="Temperature (Fahrenheit)"|
           Indicator=="Energy Use (kg, oil-eq./capita)"|
           Indicator=="CO2 Emissions (Mg)") %>%
  ggplot(aes(x=Year, y=`Change (%)`, color=Indicator)) + 
  geom_hline(yintercept=0.8, linetype=2) +
  geom_hline(yintercept=1.2, linetype=2) +
  geom_hline(yintercept = 1, linetype=3) +
  geom_line(size=1) +
  scale_x_continuous(breaks = seq(1980,2010,by=5),
                     labels = seq(1980,2010,by=5)) +
  scale_y_continuous(breaks = seq(-10,10, by=1),
                     labels = seq(-10,10, by=1),
                     limits = c(-10,10)) +
  theme_classic() +
  theme(axis.text.x = element_text(angle = 90),
        axis.title.x  = element_blank(),
        legend.position = "bottom",
        legend.direction = "horizontal") + 
  labs(title = "Emissions, Energy Use, and Temperature (1980-2010)",
       subtitle = "Change (%) Lines")

df_long_us %>%
  filter(Year>=1980) %>%
  filter(Year<=2010) %>%
  filter(Indicator=="Temperature (Fahrenheit)"|
           Indicator=="Energy Use (kg, oil-eq./capita)"|
           Indicator=="CO2 Emissions (Mg)") %>%
  ggplot(aes(x=Year, y=`Change (%)`, color=Indicator)) + 
  geom_hline(yintercept=0.8, linetype=2) +
  geom_hline(yintercept=1.2, linetype=2) +
  geom_hline(yintercept = 1, linetype=3) +
  geom_smooth(size=1, alpha=0.1, aes(fill=Indicator), se=FALSE) +
  scale_x_continuous(breaks = seq(1980,2010,by=5),
                     labels = seq(1980,2010,by=5)) +
  scale_y_continuous(breaks = seq(-10,10, by=1),
                     labels = seq(-10,10, by=1),
                     limits = c(-10,10)) +
  theme_classic() + 
  theme(axis.text.x = element_text(angle = 90),
        axis.title.x  = element_blank(),
        legend.position = "bottom",
        legend.direction = "horizontal") + 
  labs(title = "US Emissions, Energy Use, and Temperatures (1980-2010)",
       subtitle = "Smoothed Change (%) Lines")

## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

df_long_us %>%
  filter(Year>=1980) %>%
  filter(Year<=2010) %>%
  filter(Indicator=="CO2 Emissions (Mg)"|
           Indicator=="Temperature (Fahrenheit)") %>%
  ggplot(aes(x=Year, y=Value)) +
  geom_line() + 
  scale_x_continuous(breaks = seq(1980,2010,by=5),
                     labels = seq(1980,2010,by=5)) + 
  facet_wrap(Indicator~., scales = "free_y", ncol=1) +
  theme_classic() +
  theme(axis.text.x = element_text(angle = 90),
        axis.title = element_blank()) + 
  labs(title="US Emissions and Temperatures (1980-2010)")

df_long_us %>%
  filter(Indicator=="CO2 Emissions (Mg)"|
           Indicator=="Temperature (Fahrenheit)") %>%
  ggplot(aes(x=Year, y=Value)) +
  geom_vline(xintercept = 1980, linetype=2, color="black") + 
  geom_vline(xintercept = 2010, linetype=2, color="black") +
  geom_segment(aes(x=Year, y=Value, xend=Year, yend=Mean,color=Anomaly_color), size=1.25) +
  scale_color_manual(values = c("red","blue","gray")) + 
  geom_hline(aes(yintercept=Mean), linetype=1, color="black") +
  scale_x_continuous(breaks = seq(1900,2010,by=5),
                     labels = seq(1900,2010,by=5)) +
  facet_wrap(Indicator~., scales = "free_y", ncol=1) + 
  theme_classic() +
  theme(axis.text.x = element_text(angle = 90),
        axis.title = element_blank(),
        legend.position = "none")  +
  labs(title = "US Emissions and Temperatures (1900-2010)",
       subtitle = "Indicator Mean Represented by Solid Black Line")

df_long_us %>%
  filter(Indicator=="Temperature (Fahrenheit)"|
           Indicator=="CO2 Emissions (Mg)") %>%
  ggplot(aes(x=Year, y=`Change (%)`)) +
  annotate("rect", xmin=-Inf, xmax=Inf, ymin=0, ymax=Inf, alpha=0.25, fill="green") +
  annotate("rect", xmin=-Inf, xmax=Inf, ymin=-Inf, ymax=0, alpha=0.25, fill="red") +
  geom_hline(yintercept=0, linetype=1) + 
  geom_segment(aes(x=Year, y=`Change (%)`, xend=Year, yend=0), size=1.25) +
  facet_wrap(Indicator~., scales = "free_y", ncol=1) +
  scale_x_continuous(breaks = seq(1900,2010,by=5),
                     labels = seq(1900,2010,by=5)) +
  theme_classic() + 
  theme(axis.text.x = element_text(angle = 90),
        axis.title.x  = element_blank(),
        legend.position = "bottom",
        legend.direction = "horizontal") + 
  labs(title = "US Emissions, Energy Use, and Temperatures (1980-2010)",
       subtitle = "Change (%) Lines")

## Warning: Removed 2 rows containing missing values (geom_segment).